© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203278
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Ι
    0.46
    rafi
    0.45
     भाग्य
    0.44
     Rosetta
    0.44
    在庫
    0.43
    gete
    0.43
    P
    0.43
    tte
    0.43
     L
    0.42
     Fabrizio
    0.42
    POSITIVE LOGITS
    رآ
    0.53
    ان
    0.50
     specialises
    0.49
     propriétaires
    0.49
     hasn
    0.49
     آپ
    0.49
     organisations
    0.47
     operazioni
    0.47
    asság
    0.47
     OPERATION
    0.47
    Activations Density 0.000%

    No Known Activations